Model: GELU Model: 3 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1535 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.3542. Min Range: -5.3542

Max Act: 5.3542. Min Act: -0.1700

Data Index: 218193 (C4 (Web Text))

Max Activating Token Index: 823

Text #1

Max Range: 5.3542. Min Range: -5.3542

Max Act: 5.1042. Min Act: -0.1700

Data Index: 397421 (C4 (Web Text))

Max Activating Token Index: 336

Text #2

Max Range: 5.3542. Min Range: -5.3542

Max Act: 5.0730. Min Act: -0.1700

Data Index: 785987 (C4 (Web Text))

Max Activating Token Index: 826

Text #3

Max Range: 5.3542. Min Range: -5.3542

Max Act: 5.1042. Min Act: -0.1700

Data Index: 48841 (C4 (Web Text))

Max Activating Token Index: 355

Text #4

Max Range: 5.3542. Min Range: -5.3542

Max Act: 5.0417. Min Act: -0.1700

Data Index: 837098 (C4 (Web Text))

Max Activating Token Index: 194

Text #5

Max Range: 5.3542. Min Range: -5.3542

Max Act: 4.9792. Min Act: -0.1693

Data Index: 1084476 (C4 (Web Text))

Max Activating Token Index: 550

Text #6

Max Range: 5.3542. Min Range: -5.3542

Max Act: 4.9792. Min Act: -0.1700

Data Index: 981078 (C4 (Web Text))

Max Activating Token Index: 53

Text #7

Max Range: 5.3542. Min Range: -5.3542

Max Act: 4.8855. Min Act: -0.1700

Data Index: 262914 (C4 (Web Text))

Max Activating Token Index: 380

Text #8

Max Range: 5.3542. Min Range: -5.3542

Max Act: 4.8855. Min Act: -0.1700

Data Index: 423359 (C4 (Web Text))

Max Activating Token Index: 545

Text #9

Max Range: 5.3542. Min Range: -5.3542

Max Act: 4.9167. Min Act: -0.1700

Data Index: 633475 (C4 (Web Text))

Max Activating Token Index: 272

Text #10

Max Range: 5.3542. Min Range: -5.3542

Max Act: 4.8230. Min Act: -0.1699

Data Index: 1247855 (C4 (Web Text))

Max Activating Token Index: 908

Text #11

Max Range: 5.3542. Min Range: -5.3542

Max Act: 4.8855. Min Act: -0.1700

Data Index: 650680 (C4 (Web Text))

Max Activating Token Index: 724

Text #12

Max Range: 5.3542. Min Range: -5.3542

Max Act: 4.8855. Min Act: -0.1700

Data Index: 734258 (C4 (Web Text))

Max Activating Token Index: 291

Text #13

Max Range: 5.3542. Min Range: -5.3542

Max Act: 4.8855. Min Act: -0.1700

Data Index: 768323 (C4 (Web Text))

Max Activating Token Index: 449

Text #14

Max Range: 5.3542. Min Range: -5.3542

Max Act: 4.8542. Min Act: -0.1700

Data Index: 1026820 (C4 (Web Text))

Max Activating Token Index: 384

Text #15

Max Range: 5.3542. Min Range: -5.3542

Max Act: 4.8230. Min Act: -0.1700

Data Index: 611163 (C4 (Web Text))

Max Activating Token Index: 580

Text #16

Max Range: 5.3542. Min Range: -5.3542

Max Act: 4.8542. Min Act: -0.1700

Data Index: 1186360 (C4 (Web Text))

Max Activating Token Index: 722

Text #17

Max Range: 5.3542. Min Range: -5.3542

Max Act: 4.8542. Min Act: -0.1700

Data Index: 1056604 (C4 (Web Text))

Max Activating Token Index: 374

Text #18

Max Range: 5.3542. Min Range: -5.3542

Max Act: 4.8230. Min Act: -0.1700

Data Index: 1042558 (C4 (Web Text))

Max Activating Token Index: 960

Text #19

Max Range: 5.3542. Min Range: -5.3542

Max Act: 4.8230. Min Act: -0.1700

Data Index: 623954 (C4 (Web Text))

Max Activating Token Index: 929